Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
64 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
63 providers
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
46 providers
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking
61 providers
Thinking Kimi model for slower research passes, planning, and hard technical questions
22 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Kimi K2.6moonshotai/kimi-k2.6 | Moonshot AI |
45.1 | 262.144K | $0.95 | $4 | 2026-04-21 | ||
| Kimi K3moonshotai/kimi-k3 | Moonshot AI |
43.8 | 1.04858M | $3 | $15 | 2026-07-16 | ||
| MoonshotAI: Kimi K3 (batch)moonshotai/kimi-k3:batch | Moonshot AI |
43.8 | 1.04858M | $3 | $15 | — | ||
| MoonshotAI: Kimi K2.7 Code (batch)moonshotai/kimi-k2.7-code:batch | Moonshot AI |
43.0 | 262.144K | $0.95 | $4 | — | ||
| Kimi K2.5moonshotai/kimi-k2.5 | Moonshot AI |
36.0 | 262.144K | $0.3 | $1.9 | 2026-01 | ||
| Kimi K2.7 Codemoonshotai/kimi-k2.7-code | Moonshot AI |
26.3 | 262.144K | $0.95 | $4 | 2026-06-12 | ||
| Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | Moonshot AI |
17.2 | 262.144K | $0.4 | $2.5 | 2025-11-06 |